Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 6725
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or location likely associated with politics or crime

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Escobar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dynamics
    -0.72
     Jenner
    -0.67
    çİĭ
    -0.66
    ãĥĩãĤ£
    -0.65
    WARE
    -0.65
    beard
    -0.64
     GUN
    -0.64
    κ
    -0.64
    女
    -0.64
    å§«
    -0.64
    POSITIVE LOGITS
    ribed
    1.25
    apist
    1.19
    aped
    1.14
    apes
    1.08
    orts
    1.06
    aline
    1.04
    apers
    1.02
    aping
    0.99
    ribing
    0.98
    udos
    0.96
    Activations Density 0.028%

    No Known Activations